© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41973
    Prev
    Next
    INDEX
    Explanations

    package dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .xaml
    -0.08
    itev
    -0.08
    游æĪıçİ©æ³ķ
    -0.08
    TestMethod
    -0.08
    .mit
    -0.08
    innitus
    -0.08
    ç²¾ç¥ŀä¸ĬçļĦ
    -0.08
    pecia
    -0.08
    mouseover
    -0.08
    lament
    -0.08
    POSITIVE LOGITS
    ats
    0.07
     pkg
    0.06
    IGIN
    0.06
     Clarke
    0.06
    __
    0.06
     kj
    0.06
    str
    0.06
     kv
    0.06
     (($
    0.06
     &
    0.05
    Activations Density 0.047%

    No Known Activations